Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2506.18385 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913907167199232 |
|---|---|
| author | Deng, Nianchen Gu, Lixin Ye, Shenglong He, Yinan Chen, Zhe Li, Songze Wang, Haomin Wei, Xingguang Yang, Tianshuo Dou, Min He, Tong Shao, Wenqi Zhang, Kaipeng Wang, Yi Shi, Botian Zhang, Yanting Dai, Jifeng Qiao, Yu Zhang, Hongjie Wang, Wenhai |
| author_facet | Deng, Nianchen Gu, Lixin Ye, Shenglong He, Yinan Chen, Zhe Li, Songze Wang, Haomin Wei, Xingguang Yang, Tianshuo Dou, Min He, Tong Shao, Wenqi Zhang, Kaipeng Wang, Yi Shi, Botian Zhang, Yanting Dai, Jifeng Qiao, Yu Zhang, Hongjie Wang, Wenhai |
| contents | Recent benchmarks and datasets have been proposed to improve spatial reasoning in vision-language models (VLMs), yet existing open resources remain limited in scale, visual diversity, and instruction expressiveness. In this work, we introduce InternSpatial, the largest open-source dataset for spatial reasoning in VLMs, along with InternSpatial-Bench, a corresponding evaluation benchmark designed to assess spatial understanding under diverse instruction formats. InternSpatial comprises 12 million QA pairs spanning both single-view and multi-view settings, drawn from diverse visual environments and supporting 19 instruction formats that reflect varied query styles. For evaluation, we propose InternSpatial-Bench for single-view tasks and expand multi-view reasoning by introducing a novel rotation angle prediction task that has not been explored in prior work. Experimental results show that models trained on InternSpatial achieve 12.1% improvement on InternSpatial-Bench and 10.7% on VSI-Bench, while maintaining strong performance on general-purpose benchmarks. We hope these resources will support the development of spatially capable VLMs in practical applications such as robotics and embodied AI. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_18385 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | InternSpatial: A Comprehensive Dataset for Spatial Reasoning in Vision-Language Models Deng, Nianchen Gu, Lixin Ye, Shenglong He, Yinan Chen, Zhe Li, Songze Wang, Haomin Wei, Xingguang Yang, Tianshuo Dou, Min He, Tong Shao, Wenqi Zhang, Kaipeng Wang, Yi Shi, Botian Zhang, Yanting Dai, Jifeng Qiao, Yu Zhang, Hongjie Wang, Wenhai Computer Vision and Pattern Recognition Recent benchmarks and datasets have been proposed to improve spatial reasoning in vision-language models (VLMs), yet existing open resources remain limited in scale, visual diversity, and instruction expressiveness. In this work, we introduce InternSpatial, the largest open-source dataset for spatial reasoning in VLMs, along with InternSpatial-Bench, a corresponding evaluation benchmark designed to assess spatial understanding under diverse instruction formats. InternSpatial comprises 12 million QA pairs spanning both single-view and multi-view settings, drawn from diverse visual environments and supporting 19 instruction formats that reflect varied query styles. For evaluation, we propose InternSpatial-Bench for single-view tasks and expand multi-view reasoning by introducing a novel rotation angle prediction task that has not been explored in prior work. Experimental results show that models trained on InternSpatial achieve 12.1% improvement on InternSpatial-Bench and 10.7% on VSI-Bench, while maintaining strong performance on general-purpose benchmarks. We hope these resources will support the development of spatially capable VLMs in practical applications such as robotics and embodied AI. |
| title | InternSpatial: A Comprehensive Dataset for Spatial Reasoning in Vision-Language Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.18385 |